In [5]:

    

import pandas as pd


    

In [11]:

    

%matplotlib inline


    

In [17]:

    

#for encoding the command would look smth like this:
#df = pd.read_csv("XXXXXXXXXXXXXXXXX.csv", encoding='mac_roman')
df = pd.read_csv("Animal_Data/07-hw-animals.csv")


    

In [20]:

    

df.columns


    

    
Out[20]:





Index(['animal', 'name', 'length'], dtype='object')

In [21]:

    

df.head(3)


    

    
Out[21]:






  

    

      

      
animal
      
name
      
length
    
  
  

    

      
0
      
cat
      
Anne
      
35
    
    

      
1
      
cat
      
Bob
      
45
    
    

      
2
      
dog
      
Egglesburg
      
65
    
  

In [25]:

    

df.sort_values(by='length', ascending=False).head(3)


    

    
Out[25]:






  

    

      

      
animal
      
name
      
length
    
  
  

    

      
2
      
dog
      
Egglesburg
      
65
    
    

      
3
      
dog
      
Devon
      
50
    
    

      
1
      
cat
      
Bob
      
45
    
  

In [26]:

    

df['animal'].value_counts()


    

    
Out[26]:





dog    3
cat    3
Name: animal, dtype: int64

In [28]:

    

df[df['animal'] == 'dog']


    

    
Out[28]:






  

    

      

      
animal
      
name
      
length
    
  
  

    

      
2
      
dog
      
Egglesburg
      
65
    
    

      
3
      
dog
      
Devon
      
50
    
    

      
5
      
dog
      
Fontaine
      
35
    
  

In [78]:

    

df[df['length'] > 40]


    

    
Out[78]:






  

    

      

      
animal
      
name
      
length
      
feet
      
inches
    
  
  

    

      
1
      
cat
      
Bob
      
45
      
17.73
      
17.73
    
    

      
2
      
dog
      
Egglesburg
      
65
      
25.61
      
25.61
    
    

      
3
      
dog
      
Devon
      
50
      
19.70
      
19.70
    
  

In [84]:

    

del df['feet']


    

In [85]:

    

df['inches'] = df['length'] * 0.394
df.head()


    

    
Out[85]:






  

    

      

      
animal
      
name
      
length
      
inches
    
  
  

    

      
0
      
cat
      
Anne
      
35
      
13.790
    
    

      
1
      
cat
      
Bob
      
45
      
17.730
    
    

      
2
      
dog
      
Egglesburg
      
65
      
25.610
    
    

      
3
      
dog
      
Devon
      
50
      
19.700
    
    

      
4
      
cat
      
Charlie
      
32
      
12.608
    
  

In [86]:

    

dogs = df[df['animal'] == 'dog']
cats = df[df['animal'] == 'cat']


    

In [87]:

    

cats[cats['inches'] > 12]


    

    
Out[87]:






  

    

      

      
animal
      
name
      
length
      
inches
    
  
  

    

      
0
      
cat
      
Anne
      
35
      
13.790
    
    

      
1
      
cat
      
Bob
      
45
      
17.730
    
    

      
4
      
cat
      
Charlie
      
32
      
12.608
    
  

In [129]:

    

#df[df[df[df['animal'] == 'cat']'inches'] > 12]
#df[df['animal'] == 'cat']&
#df[df['inches'] > 12]

#pd.read_csv('imdb.txt')
#  .sort(columns='year')
#  .filter('year >1990')
#  .to_csv('filtered.csv')

df[(df['animal'] == 'cat') & (df['inches'] > 12)]

#3 > 2 & 4 > 3
#true  & true
#true

#3 > 2 & 4 > 3
#true  & 4 > 3

#(3 > 2) & (4 > 3)


    

    
Out[129]:






  

    

      

      
animal
      
name
      
length
      
inches
    
  
  

    

      
0
      
cat
      
Anne
      
35
      
13.790
    
    

      
1
      
cat
      
Bob
      
45
      
17.730
    
    

      
4
      
cat
      
Charlie
      
32
      
12.608
    
  

In [93]:

    

df[df['animal'] == 'cat'].describe()


    

    
Out[93]:






  

    

      

      
length
      
inches
    
  
  

    

      
count
      
3.000000
      
3.000000
    
    

      
mean
      
37.333333
      
14.709333
    
    

      
std
      
6.806859
      
2.681903
    
    

      
min
      
32.000000
      
12.608000
    
    

      
25%
      
33.500000
      
13.199000
    
    

      
50%
      
35.000000
      
13.790000
    
    

      
75%
      
40.000000
      
15.760000
    
    

      
max
      
45.000000
      
17.730000
    
  

In [94]:

    

df[df['animal'] == 'dog'].describe()


    

    
Out[94]:






  

    

      

      
length
      
inches
    
  
  

    

      
count
      
3.0
      
3.000
    
    

      
mean
      
50.0
      
19.700
    
    

      
std
      
15.0
      
5.910
    
    

      
min
      
35.0
      
13.790
    
    

      
25%
      
42.5
      
16.745
    
    

      
50%
      
50.0
      
19.700
    
    

      
75%
      
57.5
      
22.655
    
    

      
max
      
65.0
      
25.610
    
  

In [95]:

    

df.groupby(['animal'])['inches'].mean()


    

    
Out[95]:





animal
cat    14.709333
dog    19.700000
Name: inches, dtype: float64

In [96]:

    

df[df['animal'] == 'dog'].hist()


    

    
Out[96]:





array([[<matplotlib.axes._subplots.AxesSubplot object at 0x10dbe7ac8>,
        <matplotlib.axes._subplots.AxesSubplot object at 0x10dc3f860>]], dtype=object)






    

In [97]:

    

import matplotlib.pyplot as plt
plt.style.available


    

    
Out[97]:





['seaborn-darkgrid',
 'seaborn-dark',
 'seaborn-deep',
 'ggplot',
 'seaborn-whitegrid',
 'seaborn-notebook',
 'seaborn-dark-palette',
 'grayscale',
 'dark_background',
 'bmh',
 'fivethirtyeight',
 'seaborn-poster',
 'seaborn-paper',
 'seaborn-colorblind',
 'seaborn-white',
 'seaborn-ticks',
 'seaborn-bright',
 'seaborn-muted',
 'classic',
 'seaborn-talk',
 'seaborn-pastel']

In [110]:

    

plt.style.use('ggplot')


    

In [111]:

    

dogs['inches'].hist()


    

    
Out[111]:





<matplotlib.axes._subplots.AxesSubplot at 0x10e9924a8>






    

In [142]:

    

df.plot(kind='barh', x='name', y='length', legend=False)


    

    
Out[142]:





<matplotlib.axes._subplots.AxesSubplot at 0x10fe1d9e8>






    

In [146]:

    

cats_sorted = cats.sort_values(by='length', ascending=True).head(3)
cats_sorted.plot(kind='barh', x='name', y='length', legend=False)


    

    
Out[146]:





<matplotlib.axes._subplots.AxesSubplot at 0x1101df940>






    

In [ ]: